Reposted by @pierrelucbacon.bsky.socialDiego Calanzone @diadochus.bsky.social · 20/02/2025Special thanks to Biogen and CIFAR for the support, and @proceduralia.bsky.social + @pierrelucbacon.bsky.social for their valuable supervision, and to the entire Mila community for their feedback, discussions, and support. Code, paper, and models are public: github.com/ddidacus/mol...github.comGitHub - ddidacus/mol-moe: Repository for: "Training Preference-Guided Routers for Molecule Generation"Repository for: "Training Preference-Guided Routers for Molecule Generation" - ddidacus/mol-moe 041
Reposted by @pierrelucbacon.bsky.socialJack Bailey @jack-bailey.co.uk · 08/02/2025Exactly this. So much private innovation is really just repackaged public innovation. So by scrapping public funding, we risk scrapping future economic gains as well. 2229
pierrelucbacon.bsky.social @pierrelucbacon.bsky.social · 27/01/2025Again, Sutton said it first: "Verification, The Key to AI" incompleteideas.net/IncIdeas/Key... The bitter lesson became clear with LLMs, and now verification is all the rage in reasoning models. Sutton's insight (2001 !) was, as always, prescient.incompleteideas.netSelf-Verification, The Key to AI 070
pierrelucbacon.bsky.social @pierrelucbacon.bsky.social · 14/01/2025I am pretty happy with jupyter-book jupyterbook.org that I used for pierrelucbacon.com/rlbook/pierrelucbacon.comIntroduction — Practical Reinforcement Learning: From Algorithms to Applications 010
